page_captcha_ocr

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the behavioral burden. It discloses meaningful traits: 100% local execution via onnxruntime, model architecture, charset size, and how input is scoped (ref or entire viewport). It does not detail error or failure behavior, but the core operational transparency is strong.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded, starting with the tool's purpose and then adding model detail, execution model, input behavior, and downstream usage. Every sentence adds value; the efficiency and 'stronger than generic OCR' note reinforces selection without padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema, the description still communicates the return value ('returns the recognized text') and the practical next step ('feed it into the answer field and submit'). It provides enough for an agent to invoke correctly, though it could briefly mention limitations or failure cases for unusual captcha types.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33%, so the description must compensate. It explains the most meaningful parameter, ref, including the omit-for-viewport behavior. However, it adds no meaning for the required session_id and page_id parameters, which remain undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific operation (OCR/classify text) and resource (normal image captcha, distorted-text family), and distinguishes the tool by naming the specialized ddddocr model and contrasting with generic OCR. This clearly separates it from siblings like page_ocr and captcha_solve.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives concrete usage context: use for normal distorted-text image captchas, feed the img ref or whole viewport, and pass the result into the answer field. It does not explicitly name sibling tools or exclusion cases, but the 'normal image captcha (distorted-text family)' phrasing provides a clear selection criterion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.